https://blog.sagamiyun.me • This is a web feed, also known as an Atom feed. Subscribe by copying the URL from the address bar into your newsreader. Visit About Feeds to learn more and get started. It's free. Visit website Recent posts Updated on $DATE dark date ollama Kit Kyo - ollama Full-stack engineer · DevOps · agent development — currently going deep on ML & infrastructure. Zola2026-06-15T00:00:00+00:00https://blog.sagamiyun.me/tags/ollama/atom.xml Your edge LLM can't tell time — and a 40-line memory can fix it (for some models) 2026-06-15T00:00:00+00:00 2026-06-15T00:00:00+00:00 Kit Kyo · A2O Labs https://blog.sagamiyun.me/blog/edge-llm-cant-tell-time/ A tiny adversarial benchmark shows small local LLMs confuse token-distance for elapsed wall-clock time. A zero-dependency continuous-time memory fixes it for sub-millisecond cost — but whether a model will even accept that fix turns out to be a model-dependent deployability property that capability leaderboards don't measure.